mlsanityData to 7 Oct 2026

Augmentation-Free Self-Supervised Learning on Graphs

arXiv 2112.02472 ↗First posted 5 Dec 2021cs.LG cs.AIcited by 94

Not on the map. Why?

Abstract (arXiv)

Inspired by the recent success of self-supervised methods applied on images, self-supervised learning on graph structured data has seen rapid growth especially centered on augmentation-based contrastive methods. However, we argue that without carefully designed augmentation techniques, augmentations on graphs may behave arbitrarily in that the underlying semantics of graphs can drastically change. As a consequence, the performance of existing augmentation-based methods is highly dependent on the choice of augmentation scheme, i.e., hyperparameters associated with augmentations. In this paper, we propose a novel augmentation-free self-supervised learning framework for graphs, named AFGRL. Specifically, we generate an alternative view of a graph by discovering nodes that share the local structural information and the global semantics with the graph. Extensive experiments towards various node-level tasks, i.e., node classification, clustering, and similarity search on various real-world datasets demonstrate the superiority of AFGRL. The source code for AFGRL is available at https://github.com/Namkyeong/AFGRL.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 41 of its 47 references that are in the map. First posted on arXiv 5 Dec 2021.

Builds on

41 of 47 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Graph Attention Networkscited by 8,854
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  11. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  12. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
29 more
  1. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  2. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  4. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  6. 2018Deep Graph Infomaxcited by 1,101
  7. 2015Image-based Recommendations on Styles and Substitutescited by 702
  8. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  9. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  10. 2020Deep Graph Contrastive Representation Learningcited by 535
  11. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  12. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  13. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  14. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  15. 2021Graph Contrastive Learning Automatedcited by 287
  16. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  17. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  18. 2020Data Augmentation for Graph Neural Networkscited by 200
  19. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  20. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  21. 2020Uncovering the structure of clinical EEG signals with self-supervised learningcited by 109
  22. 2020Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learningcited by 90
  23. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  24. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  25. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  26. 2021Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learningcited by 70
  27. 2021Prototypical Graph Contrastive Learningcited by 37
  28. 2021Self-supervised Graph Neural Networks without explicit negative samplingcited by 25
  29. 2019Self-supervised representation learning from electroencephalography signalscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 22; 2023: 28; 2024: 20; 2025: 19; 2026: 5.

94 papers.

Sort:

By area:

  1. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  2. 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
  3. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  4. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  5. 2022Hard Sample Aware Network for Contrastive Deep Graph Clusteringcited by 61
  6. 2023Cluster-guided Contrastive Graph Clustering Networkcited by 60
  7. 2022Simple Contrastive Graph Clusteringcited by 56
  8. 2022Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrumcited by 43
  9. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  10. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  11. 2023Dink-Net: Neural Clustering on Large Graphscited by 38
  12. 2023GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphscited by 28
38 more
  1. 2022A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resourcecited by 26
  2. 2023CONVERT:Contrastive Graph Clustering with Reliable Augmentationcited by 23
  3. 2023ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detectioncited by 23
  4. 2022Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representationscited by 21
  5. 2023Graph-level Representation Learning with Joint-Embedding Predictive Architecturescited by 21
  6. 2023HomoGCL: Rethinking Homophily in Graph Contrastive Learningcited by 18
  7. 2024Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspectivecited by 18
  8. 2022Graph Soft-Contrastive Learning via Neighborhood Rankingcited by 16
  9. 2022Heterogeneous Graph Learning for Multi-modal Medical Data Analysiscited by 16
  10. 2023Reinforcement Graph Clustering with Unknown Cluster Numbercited by 16
  11. 2024GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Modelscited by 16
  12. 2023Shift-Robust Molecular Relational Learning with Causal Substructurecited by 15
  13. 2022Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graphcited by 14
  14. 2023Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networkscited by 14
  15. 2024PyG-SSL: A Graph Self-Supervised Learning Toolkitcited by 14
  16. 2022Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learningcited by 13
  17. 2023STERLING: Synergistic Representation Learning on Bipartite Graphscited by 12
  18. 2022Relational Self-Supervised Learning on Graphscited by 11
  19. 2024Robust Graph Structure Learning under Heterophilycited by 11
  20. 2024Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneckcited by 11
  21. 2025One Prompt Fits All: Universal Graph Adaptation for Pretrained Modelscited by 11
  22. 2022GraphLearner: Graph Node Clustering with Fully Learnable Augmentationcited by 10
  23. 2022Localized Contrastive Learning on Graphscited by 10
  24. 2023RARE: Robust Masked Graph Autoencodercited by 10
  25. 2023Rethinking and Simplifying Bootstrapped Graph Latentscited by 10
  26. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  27. 2022Generative Subgraph Contrast for Self-Supervised Graph Representation Learningcited by 8
  28. 2023GUESR: A Global Unsupervised Data-Enhancement with Bucket-Cluster Sampling for Sequential Recommendationcited by 8
  29. 2023Task-Equivariant Graph Few-shot Learningcited by 8
  30. 2022Graph Contrastive Learning with Implicit Augmentationscited by 7
  31. 2023CSGCL: Community-Strength-Enhanced Graph Contrastive Learningcited by 7
  32. 2025Towards A Universal Graph Structural Encodercited by 7
  33. 2023Similarity Preserving Adversarial Graph Contrastive Learningcited by 6
  34. 2024Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learningcited by 6
  35. 2023CARL-G: Clustering-Accelerated Representation Learning on Graphscited by 5
  36. 2024Negative-Free Self-Supervised Gaussian Embedding of Graphscited by 5
  37. 2025Rethinking Graph Contrastive Learning through Relative Similarity Preservationcited by 5
  38. 2023GraphCL-DTA: a graph contrastive learning with molecular semantics for drug-target binding affinity predictioncited by 4

50 most cited of 94 All 94 (JSON)